Scan reports · 13,703 stars
Orchestra-Research/AI-Research-SKILLs, scanned
40 skills from Orchestra-Research/AI-Research-SKILLs, average score 83/100, 3 with a critical finding. Scanned 2026-10-19.
Best score first
Every skill
- distributed-llm-pretraining-torchtitanSecurity 25/252,083 tokensGrade A96/100
- fine-tuning-with-trlSecurity 25/252,715 tokensGrade A96/100
- implementing-llms-litgptSecurity 25/252,603 tokensGrade A96/100
- modal-serverless-gpuSecurity 25/252,038 tokensGrade A96/100
- nemo-curatorSecurity 25/252,165 tokensGrade A96/100
- nnsight-remote-interpretabilitySecurity 25/253,132 tokensGrade A96/100
- peft-fine-tuningSecurity 25/252,899 tokensGrade A96/100
- pytorch-lightningSecurity 25/252,140 tokensGrade A96/100
- pyvene-interventionsSecurity 25/253,403 tokensGrade A96/100
- ray-dataSecurity 25/251,683 tokensGrade A96/100
- simpo-trainingSecurity 25/251,338 tokensGrade A96/100
- sparse-autoencoder-trainingSecurity 25/253,042 tokensGrade A96/100
- transformer-lens-interpretabilitySecurity 25/252,868 tokensGrade A96/100
- slime-rl-trainingSecurity 25/252,648 tokensGrade A92/100
- training-llms-megatronSecurity 25/252,262 tokensGrade A92/100
- nanogptSecurity 25/251,551 tokensGrade A90/100
- rwkv-architectureSecurity 25/251,631 tokensGrade A90/100
- awq-quantizationSecurity 25/251,940 tokensGrade B88/100
- huggingface-tokenizersSecurity 25/253,251 tokensGrade B88/100
- sentencepieceSecurity 17/251,250 tokensGrade B88/100
- pytorch-fsdp2Security 25/252,606 tokensGrade B87/100
- huggingface-accelerateSecurity 25/251,946 tokensGrade B86/100
- openrlhf-trainingSecurity 15/251,962 tokensGrade B86/100
- torchforge-rl-trainingSecurity 15/252,368 tokensGrade B82/100
- unslothSecurity 25/25479 tokensGrade B82/100
- constitutional-aiSecurity 25/251,907 tokensGrade B80/100
- miles-rl-trainingSecurity 25/252,101 tokensGrade B80/100
- llamaguardSecurity 25/252,163 tokensGrade C78/100
- prompt-guardSecurity 13/252,235 tokensGrade C78/100
- verl-rl-trainingSecurity 15/252,322 tokensGrade C78/100
- ray-trainSecurity 13/252,524 tokensGrade C76/100
- mamba-architectureSecurity 25/251,696 tokensGrade C72/100
- llama-factorySecurity 17/25513 tokensGrade D68/100
- nemo-guardrailsSecurity 13/251,772 tokensGrade D66/100
- lambda-labs-gpu-cloudSecurity 0/252,920 tokensGrade F63/100
- autoresearchSecurity 3/255,982 tokensGrade D60/100
- deepspeedSecurity 15/2536,030 tokensGrade F59/100
- skypilot-multi-cloud-orchestrationSecurity 0/252,294 tokensGrade F59/100
- grpo-rl-trainingSecurity 0/254,196 tokensGrade F57/100
- axolotlSecurity 0/251,094 tokensGrade F53/100
FAQ
Questions
- Is the skill's text copied here?
- No. Each report keeps only the score, the findings and facts about the source. Get the skills themselves from Orchestra-Research/AI-Research-SKILLs on GitHub.
- How current are these scores?
- Scanned 2026-10-19. The list is rebuilt from GitHub on a schedule; paste a newer version into the scanner for a fresh score.
Related
Keep reading
Free tool
Scan your own skill
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.